Narrative Analytics: Telling the Story behind the data

叙事分析：讲述数据背后的故事

• 批准号: 1729919
• 金额: --
• 依托单位: University of Bristol
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2016
• 资助国家: 英国
• 起止时间: 2016 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-1729919
• 关键词: Narrative; Analytics; Telling; Story; behind

The project aims at developing methods and a tool capable of generating Narrative Analysis of spatio-temporal data: a succinct natural language description of a selected time-space window of the data of interest. In healthcare and smart house scenarios, such techniques can be combined with activity recognition models to generate comprehensible descriptions of monitored activities with terminology and level of detail tuned to a particular recipient. In the context of the SPHERE IRC led by the University of Bristol and funded by EPSRC these techniques would facilitate making sense from acquired data for healthcare applications in a more transparent way than is possible with black-box approaches.

该项目旨在开发能够生成时空数据叙述性分析的方法和工具：对感兴趣数据的选定时空窗口进行简明的自然语言描述。在医疗保健和智能家居场景中，可以将此类技术与活动识别模型相结合，以生成受监视活动的可理解描述，并根据特定接收者调整术语和详细程度。在由布里斯托尔大学领导并由EPSRC资助的SPERE IRC的背景下，这些技术将有助于以比黑盒方法更透明的方式从医疗保健应用程序的获取数据中获得意义。

项目成果

FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems

FAT Forensics：用于在预测系统中实施和部署公平性、责任性和透明度算法的 Python 工具箱

• DOI: 10.21105/joss.01904
• 发表时间: 2020
• 期刊: Journal of Open Source Software
• 作者: Sokol K

Explainability fact sheets

可解释性情况说明书

• DOI: 10.1145/3351095.3372870
• 发表时间: 2020
• 作者: Sokol K

Desiderata for Interpretability: Explaining Decision Tree Predictions with Counterfactuals

可解释性的必要条件：用反事实解释决策树预测

• DOI: 10.1609/aaai.v33i01.330110035
• 发表时间: 2019
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Sokol K

Conversational Explanations of Machine Learning Predictions Through Class-contrastive Counterfactual Statements

通过类对比反事实陈述对机器学习预测进行会话解释

• DOI: 10.24963/ijcai.2018/836
• 发表时间: 2018
• 作者: Sokol K

One Explanation Does Not Fit All The Promise of Interactive Explanations for Machine Learning Transparency

一种解释并不能满足交互式解释对机器学习透明度的所有承诺

• DOI: 10.1007/s13218-020-00637-y
• 发表时间: 2020
• 期刊: KI - Künstliche Intelligenz
• 作者: Sokol K